agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v10 1/3] Allow CREATE INDEX CONCURRENTLY on partitioned table
147+ messages / 3 participants
[nested] [flat]

* [PATCH v10 1/3] Allow CREATE INDEX CONCURRENTLY on partitioned table
@ 2020-06-06 22:42  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Justin Pryzby @ 2020-06-06 22:42 UTC (permalink / raw)

Note, this effectively reverts 050098b14, so take care to not reintroduce the
bug it fixed.

XXX: does pgstat_progress_update_param() break other commands progress ?
---
 doc/src/sgml/ref/create_index.sgml     |   9 --
 src/backend/commands/indexcmds.c       | 141 ++++++++++++++++++-------
 src/test/regress/expected/indexing.out |  60 ++++++++++-
 src/test/regress/sql/indexing.sql      |  18 +++-
 4 files changed, 172 insertions(+), 56 deletions(-)

diff --git a/doc/src/sgml/ref/create_index.sgml b/doc/src/sgml/ref/create_index.sgml
index 749db2845e..ba4424d379 100644
--- a/doc/src/sgml/ref/create_index.sgml
+++ b/doc/src/sgml/ref/create_index.sgml
@@ -661,15 +661,6 @@ Indexes:
     cannot.
    </para>
 
-   <para>
-    Concurrent builds for indexes on partitioned tables are currently not
-    supported.  However, you may concurrently build the index on each
-    partition individually and then finally create the partitioned index
-    non-concurrently in order to reduce the time where writes to the
-    partitioned table will be locked out.  In this case, building the
-    partitioned index is a metadata only operation.
-   </para>
-
   </refsect2>
  </refsect1>
 
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index 996f1ed070..c1dd4c8362 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -93,6 +93,7 @@ static bool ReindexRelationConcurrently(Oid relationOid, int options);
 
 static void ReindexPartitions(Oid relid, int options, bool isTopLevel);
 static void ReindexMultipleInternal(List *relids, int options);
+static void reindex_invalid_child_indexes(Oid indexRelationId);
 static void reindex_error_callback(void *args);
 static void update_relispartition(Oid relationId, bool newval);
 static bool CompareOpclassOptions(Datum *opts1, Datum *opts2, int natts);
@@ -667,17 +668,6 @@ DefineIndex(Oid relationId,
 	partitioned = rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE;
 	if (partitioned)
 	{
-		/*
-		 * Note: we check 'stmt->concurrent' rather than 'concurrent', so that
-		 * the error is thrown also for temporary tables.  Seems better to be
-		 * consistent, even though we could do it on temporary table because
-		 * we're not actually doing it concurrently.
-		 */
-		if (stmt->concurrent)
-			ereport(ERROR,
-					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("cannot create index on partitioned table \"%s\" concurrently",
-							RelationGetRelationName(rel))));
 		if (stmt->excludeOpNames)
 			ereport(ERROR,
 					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -1111,6 +1101,11 @@ DefineIndex(Oid relationId,
 		if (pd->nparts != 0)
 			flags |= INDEX_CREATE_INVALID;
 	}
+	else if (concurrent && OidIsValid(parentIndexId))
+	{
+		/* If concurrent, initially build index partitions as "invalid" */
+		flags |= INDEX_CREATE_INVALID;
+	}
 
 	if (stmt->deferrable)
 		constr_flags |= INDEX_CONSTR_CREATE_DEFERRABLE;
@@ -1163,6 +1158,14 @@ DefineIndex(Oid relationId,
 		 */
 		if (!stmt->relation || stmt->relation->inh)
 		{
+			/*
+			 * Need to close the relation before recursing into children, so
+			 * copy needed data into a longlived context.
+			 */
+
+			MemoryContext	ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX",
+					ALLOCSET_DEFAULT_SIZES);
+			MemoryContext	oldcontext = MemoryContextSwitchTo(ind_context);
 			PartitionDesc partdesc = RelationGetPartitionDesc(rel);
 			int			nparts = partdesc->nparts;
 			Oid		   *part_oids = palloc(sizeof(Oid) * nparts);
@@ -1170,12 +1173,15 @@ DefineIndex(Oid relationId,
 			TupleDesc	parentDesc;
 			Oid		   *opfamOids;
 
+			// If concurrent, maybe this should be done after excluding indexes which already exist ?
 			pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_TOTAL,
 										 nparts);
 
 			memcpy(part_oids, partdesc->oids, sizeof(Oid) * nparts);
+			parentDesc = CreateTupleDescCopy(RelationGetDescr(rel));
+			table_close(rel, NoLock);
+			MemoryContextSwitchTo(oldcontext);
 
-			parentDesc = RelationGetDescr(rel);
 			opfamOids = palloc(sizeof(Oid) * numberOfKeyAttributes);
 			for (i = 0; i < numberOfKeyAttributes; i++)
 				opfamOids[i] = get_opclass_family(classObjectId[i]);
@@ -1218,10 +1224,12 @@ DefineIndex(Oid relationId,
 					continue;
 				}
 
+				oldcontext = MemoryContextSwitchTo(ind_context);
 				childidxs = RelationGetIndexList(childrel);
 				attmap =
 					build_attrmap_by_name(RelationGetDescr(childrel),
 										  parentDesc);
+				MemoryContextSwitchTo(oldcontext);
 
 				foreach(cell, childidxs)
 				{
@@ -1292,10 +1300,14 @@ DefineIndex(Oid relationId,
 				 */
 				if (!found)
 				{
-					IndexStmt  *childStmt = copyObject(stmt);
+					IndexStmt  *childStmt;
 					bool		found_whole_row;
 					ListCell   *lc;
 
+					oldcontext = MemoryContextSwitchTo(ind_context);
+					childStmt = copyObject(stmt);
+					MemoryContextSwitchTo(oldcontext);
+
 					/*
 					 * We can't use the same index name for the child index,
 					 * so clear idxname to let the recursive invocation choose
@@ -1347,10 +1359,18 @@ DefineIndex(Oid relationId,
 								createdConstraintId,
 								is_alter_table, check_rights, check_not_in_use,
 								skip_build, quiet);
+					if (concurrent)
+					{
+						PopActiveSnapshot();
+						PushActiveSnapshot(GetTransactionSnapshot());
+						invalidate_parent = true;
+					}
 				}
 
-				pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
-											 i + 1);
+				/* For concurrent build, this is a catalog-only stage */
+				if (!concurrent)
+					pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+												 i + 1);
 				free_attrmap(attmap);
 			}
 
@@ -1360,51 +1380,42 @@ DefineIndex(Oid relationId,
 			 * invalid, this is incorrect, so update our row to invalid too.
 			 */
 			if (invalidate_parent)
-			{
-				Relation	pg_index = table_open(IndexRelationId, RowExclusiveLock);
-				HeapTuple	tup,
-							newtup;
-
-				tup = SearchSysCache1(INDEXRELID,
-									  ObjectIdGetDatum(indexRelationId));
-				if (!HeapTupleIsValid(tup))
-					elog(ERROR, "cache lookup failed for index %u",
-						 indexRelationId);
-				newtup = heap_copytuple(tup);
-				((Form_pg_index) GETSTRUCT(newtup))->indisvalid = false;
-				CatalogTupleUpdate(pg_index, &tup->t_self, newtup);
-				ReleaseSysCache(tup);
-				table_close(pg_index, RowExclusiveLock);
-				heap_freetuple(newtup);
-			}
-		}
+				index_set_state_flags(indexRelationId, INDEX_DROP_CLEAR_VALID);
+		} else
+			table_close(rel, NoLock);
 
 		/*
 		 * Indexes on partitioned tables are not themselves built, so we're
 		 * done here.
 		 */
-		table_close(rel, NoLock);
 		if (!OidIsValid(parentIndexId))
+		{
+			if (concurrent)
+				reindex_invalid_child_indexes(indexRelationId);
+
 			pgstat_progress_end_command();
+		}
+
 		return address;
 	}
 
-	if (!concurrent)
+	table_close(rel, NoLock);
+	if (!concurrent || OidIsValid(parentIndexId))
 	{
-		/* Close the heap and we're done, in the non-concurrent case */
-		table_close(rel, NoLock);
+		/*
+		 * We're done if this is the top-level index,
+		 * or the catalog-only phase of a partition built concurrently
+		 */
 
-		/* If this is the top-level index, we're done. */
 		if (!OidIsValid(parentIndexId))
 			pgstat_progress_end_command();
 
 		return address;
 	}
 
-	/* save lockrelid and locktag for below, then close rel */
+	/* save lockrelid and locktag for below */
 	heaprelid = rel->rd_lockInfo.lockRelId;
 	SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId);
-	table_close(rel, NoLock);
 
 	/*
 	 * For a concurrent build, it's important to make the catalog entries
@@ -1586,6 +1597,56 @@ DefineIndex(Oid relationId,
 	return address;
 }
 
+/* Reindex invalid child indexes created earlier */
+static void
+reindex_invalid_child_indexes(Oid indexRelationId)
+{
+	ListCell *lc;
+	int		npart = 0;
+
+	MemoryContext	ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX",
+			ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcontext;
+	List		*childs = find_inheritance_children(indexRelationId, ShareLock);
+	List		*partitions = NIL;
+
+	PreventInTransactionBlock(true, "REINDEX INDEX");
+
+	foreach (lc, childs)
+	{
+		Oid			partoid = lfirst_oid(lc);
+
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE,
+									 npart++);
+
+		if (get_index_isvalid(partoid) ||
+				!RELKIND_HAS_STORAGE(get_rel_relkind(partoid)))
+			continue;
+
+		/* Save partition OID */
+		oldcontext = MemoryContextSwitchTo(ind_context);
+		partitions = lappend_oid(partitions, partoid);
+		MemoryContextSwitchTo(oldcontext);
+	}
+
+	/*
+	 * Process each partition listed in a separate transaction.  Note that
+	 * this commits and then starts a new transaction immediately.
+	 */
+	ReindexMultipleInternal(partitions, REINDEXOPT_CONCURRENTLY);
+
+	/*
+	 * CIC needs to mark a partitioned index as VALID, which itself
+	 * requires setting READY, which is unset for CIC (even though
+	 * it's meaningless for an index without storage).
+	 * This must be done only while holding a lock which precludes adding
+	 * partitions.
+	 * See also: validatePartitionedIndex().
+	 */
+	index_set_state_flags(indexRelationId, INDEX_CREATE_SET_READY);
+	CommandCounterIncrement();
+	index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID);
+}
 
 /*
  * CheckMutability
diff --git a/src/test/regress/expected/indexing.out b/src/test/regress/expected/indexing.out
index 49b6f7c18f..2fb00a2fa7 100644
--- a/src/test/regress/expected/indexing.out
+++ b/src/test/regress/expected/indexing.out
@@ -50,11 +50,63 @@ select relname, relkind, relhassubclass, inhparent::regclass
 (8 rows)
 
 drop table idxpart;
--- Some unsupported features
+-- CIC on partitioned table
 create table idxpart (a int, b int, c text) partition by range (a);
-create table idxpart1 partition of idxpart for values from (0) to (10);
-create index concurrently on idxpart (a);
-ERROR:  cannot create index on partitioned table "idxpart" concurrently
+create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a);
+create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a);
+create table idxpart111 partition of idxpart11 default partition by range(a);
+create table idxpart1111 partition of idxpart111 default partition by range(a);
+create table idxpart2 partition of idxpart for values from (10) to (20);
+insert into idxpart2 values(10),(10); -- not unique
+create index concurrently on idxpart (a); -- partitioned
+create index concurrently on idxpart1 (a); -- partitioned and partition
+create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves
+create index concurrently on idxpart2 (a); -- leaf
+create unique index concurrently on idxpart (a); -- partitioned, unique failure
+ERROR:  could not create unique index "idxpart2_a_idx2_ccnew"
+DETAIL:  Key (a)=(10) is duplicated.
+\d idxpart
+        Partitioned table "public.idxpart"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+ b      | integer |           |          | 
+ c      | text    |           |          | 
+Partition key: RANGE (a)
+Indexes:
+    "idxpart_a_idx" btree (a)
+    "idxpart_a_idx1" UNIQUE, btree (a) INVALID
+Number of partitions: 2 (Use \d+ to list them.)
+
+\d idxpart1
+        Partitioned table "public.idxpart1"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+ b      | integer |           |          | 
+ c      | text    |           |          | 
+Partition of: idxpart FOR VALUES FROM (0) TO (10)
+Partition key: RANGE (a)
+Indexes:
+    "idxpart1_a_idx" btree (a) INVALID
+    "idxpart1_a_idx1" btree (a)
+    "idxpart1_a_idx2" UNIQUE, btree (a) INVALID
+Number of partitions: 1 (Use \d+ to list them.)
+
+\d idxpart2
+              Table "public.idxpart2"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+ b      | integer |           |          | 
+ c      | text    |           |          | 
+Partition of: idxpart FOR VALUES FROM (10) TO (20)
+Indexes:
+    "idxpart2_a_idx" btree (a)
+    "idxpart2_a_idx1" btree (a)
+    "idxpart2_a_idx2" UNIQUE, btree (a) INVALID
+    "idxpart2_a_idx2_ccnew" UNIQUE, btree (a) INVALID
+
 drop table idxpart;
 -- Verify bugfix with query on indexed partitioned table with no partitions
 -- https://postgr.es/m/[email protected]
diff --git a/src/test/regress/sql/indexing.sql b/src/test/regress/sql/indexing.sql
index fc1479dca6..610c12de9e 100644
--- a/src/test/regress/sql/indexing.sql
+++ b/src/test/regress/sql/indexing.sql
@@ -29,10 +29,22 @@ select relname, relkind, relhassubclass, inhparent::regclass
 	where relname like 'idxpart%' order by relname;
 drop table idxpart;
 
--- Some unsupported features
+-- CIC on partitioned table
 create table idxpart (a int, b int, c text) partition by range (a);
-create table idxpart1 partition of idxpart for values from (0) to (10);
-create index concurrently on idxpart (a);
+create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a);
+create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a);
+create table idxpart111 partition of idxpart11 default partition by range(a);
+create table idxpart1111 partition of idxpart111 default partition by range(a);
+create table idxpart2 partition of idxpart for values from (10) to (20);
+insert into idxpart2 values(10),(10); -- not unique
+create index concurrently on idxpart (a); -- partitioned
+create index concurrently on idxpart1 (a); -- partitioned and partition
+create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves
+create index concurrently on idxpart2 (a); -- leaf
+create unique index concurrently on idxpart (a); -- partitioned, unique failure
+\d idxpart
+\d idxpart1
+\d idxpart2
 drop table idxpart;
 
 -- Verify bugfix with query on indexed partitioned table with no partitions
-- 
2.17.0


--i3lJ51RuaGWuFYNw
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v10-0002-Add-SKIPVALID-flag-for-more-integration.patch"



^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56  Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 147+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 147+ messages in thread